On-line tuning PID parameters in an idling engine based on a modified BP neural network by particle swarm optimization

Artificial Life and Robotics - Tập 14 - Trang 129-133 - 2009
Jia-Meng Yin1, Ji-Sun Shin1, Hee-Hyol Lee1
1Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan

Tóm tắt

PID control systems are widely used in many fields, and many methods to tune the parameters of PID controllers are known. When the characteristics of the object are changed, the traditional PID control should be adjusted by empirical knowledge. This may result in a worse performance by the system. In this article, a new method to tune PID parameters, called the back-propagation network modified by particle swarm optimization, is proposed. This algorithm combines conventional PID control with a back propagation neural network (BPNN) and particle swarm optimization (PSO). This method is demonstrated in the engine idling-speed control problem. The proposed method provides considerable performance benefits compared with a traditional controller in this simulation.

Tài liệu tham khảo

Takahashi T, Ueno T, Yamamoto A, et al (1985) A simple engine model for idle speed control. [R], SAE 850291, 2.769–2.776 Cook JA, Powell BK (1988) Modeling of an internal combustion engine for control analysis. IEEE Control Syst Mag 8(4):20–26 Chen J (1996) A study of neurocontrol theory and its industrial applications, Ph.D. Dissertation, Zhejiang University, Hangzhou, China Miller III WT, Sutton RS, Werbos PJ (1990) Neural network for control. MIT Press, Cambridge Norgaard N, Ravn O, Poulsen NK, et al (2000) Neural networks for modeling and control of dynamic systems. Springer, London Hagan MT, Demuth HB, Beale MH (1995) Neural network design. PWS Publishing Yang W, QangLi Q (2004) Summarization of PSO. Chin Eng Sci 6(5):87–94 Zeng JC, Jie J, Cui ZH (2004) The algorithm of particle swarm. Press of Science, Beijing MathWorks (2005) Neural network toolbox: user’s guide 2.0